add_directory · Mcp Elevenreader MCP: Risk & Policy

WHAT IT DOES

What add_directory does on Mcp Elevenreader

AI agents use add_directory to create or update resources in Mcp Elevenreader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Elevenreader environment.

WHY IT NEEDS A POLICY

Why add_directory needs a policy

This tool creates new document records in the TTS service by uploading multiple files from a directory. This is a Write operation because it modifies the service state by adding new documents. Severity is medium because bulk uploads could consume resources or storage quota, but the operation is reversible (suggested by the presence of delete_read on the sibling tools list).

From the tool's definition Tool description states "Upload all books from a directory" - the word "upload" indicates creation/modification of data in the ElevenReader system. The tool adds document collections rather than retrieving or querying existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_directory Rate-limited

add_directory stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_directory": {
      "limits": [
        {
          "counter": "add_directory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Elevenreader, so you can run agents against it safely.

FAQ

Questions about add_directory

What does the add_directory tool do? +

Upload all books from a directory (and subdirectories). Files are sorted by name so parts (ч1, ч2) stay together. It is categorised as a Write tool in the Mcp Elevenreader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_directory? +

Register the Mcp Elevenreader MCP server in PolicyLayer and add a rule for add_directory: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Elevenreader. Nothing to install.

What risk level is add_directory? +

add_directory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_directory? +

Yes. Add a rate_limit block to the add_directory rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block add_directory completely? +

Set action: deny in the PolicyLayer policy for add_directory. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides add_directory? +

add_directory is provided by the Mcp Elevenreader MCP server (mit9/mcp-elevenreader). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.